How payment integrity tools can help payers to tackle fraud, waste and abuse
- Jun 25, 2025
- 3 min read
Although telehealth offers many benefits for patients, it introduces operational complexities for providers and creates legitimate concerns about fraud, waste, and abuse for payers.
The United States spends an average of $3.8 trillion per year on healthcare. Some estimate that fraud, waste, and abuse (FWA) costs the nation at least $114 billion annually — representing more than 3% of overall healthcare spending.
So, what can payers and providers do to reduce the massive amount of overspending? To start, let’s define FWA.
Defining fraud, waste, and abuse
Fraud: An intentional deception or misrepresentation to defraud a healthcare benefit program for unauthorized benefit or payment. This involves knowingly, willfully, and intentionally making false statements or misrepresenting material facts.
Examples include purposely billing for a service that was never performed, billing for a service with a higher reimbursement than the service provided, or altering claim forms or electronic medical records.
Waste: A misuse or over-utilization of resources, services, or practices that lead to unnecessary costs. For example, providing services that are not medically necessary.
Abuse: Provider practices that are inconsistent with sound fiscal, business, or medical practices, resulting in mistaken or unnecessary costs; reimbursement for services that aren’t medically necessary; or services that fail to meet professionally recognized standards for healthcare. Abuse is similar to fraud, except that there is no requirement to prove the abusive acts were committed knowingly, willfully, and intentionally.
For example, billing for a non-covered service, misusing codes on a claim, or inappropriately allocating costs on a cost report.
Understanding the complexity of the healthcare system
It’s important to understand different types of FWA and how they differ before we can address the massive overspending in healthcare. This is not a new trend, but as the healthcare system has become increasingly complex in recent years, we tend to see instances of waste increase as well.
Increases or changes in regulation, such as a new administration, a change in policies, or a new guideline from CMS, introduce complexity to the system. The lack of understanding among providers often leads to incorrect billing.
For example, telemedicine use exploded during the COVID-19 pandemic, with providers seeing 50 to 175 times as many patients via telehealth as before. As a result, CMS introduced several policy waivers and expansions to accommodate the surge in telehealth services.
Although telehealth offers many benefits for patients, it introduces operational complexities for providers and creates legitimate concerns about fraud, waste, and abuse for payers.
On the other hand, we also see increased instances of fraud, which is a more intentional act, primarily committed by exploiting loopholes in the guidelines to obtain higher reimbursement. The Office of Inspector General claims that the United States lost over $6 billion due to a single telemedicine-related fraud case. The uptick in telemedicine amid the COVID-19 pandemic has escalated the risk of FWA.
Turning to technology to combat fraud, waste, and abuse
When it comes to improper billing or misrepresentation of services performed, it is incumbent upon payers to identify these cases of FWA – or risk overpayment. The practice of identifying instances of FWA to increase payment accuracy and reduce overall spending waste is often referred to as payment integrity. Precise, end-to-end payment integrity has never been more essential to health plan operational costs, so the question becomes, how can resource-constrained payers tackle payment integrity efficiently and cost-effectively? Technology can help.
Natural language processing (NLP) capabilities, combined with machine learning (ML) methodologies, can be applied to train systems to function as human auditors, identifying overpayments and billing inaccuracies.
When reports come in from providers, auditors will review specific portions of the claim (such as medical records) and capture all the provider’s notes on the backend. From there, the machine starts learning trends in the reports and creating new ML algorithms that help identify outliers or mistakes in future claims.
As a result, by deploying NLP and ML techniques, organizations can reduce the manual effort previously required and identify which claims are paid or are suspected instances of FWA.
Now is the time for payers to double down on payment integrity solutions to prevent errors that lead to inflated or unnecessary spending.